Improving robustness against electrode shift of sEMG based hand gesture recognition using online semi-supervised learning

Q. X. Li, P. P. Chan, Dalin Zhou, Yinfeng Fang, Honghai Liu

Research output: Chapter in Book/Report/Conference proceedingConference contribution

162 Downloads (Pure)

Abstract

Electrode shift of a prosthetic device is one of most challengeable problems in surface Electromyography (sEMG) based hand gesture recognition. Electrode shift is usually caused by repositioning, donning or doffing of a prosthetic device. Accuracy of gesture recognition may significantly drop since a pattern of collected signals may change after electrode shift. Although re-training a recognition system after every reposition is able to maintain accurate recognition, collecting labeled samples is inconvenient to users. In this paper, we apply an online semi-supervised learning in which a classifier is trained with a small amount of labeled samples and then is updated with unlabeled samples online to hand gesture recognition. A well-known online semi-supervised learning algorithm, online multi-channel semi-supervised growing neural gas (OSSMGNG) algorithm, is used in this preliminary study. OSSMGNG is compared with an intuitive method which learns from the initial label training set only in experiments. The data is collected from able-bodied individuals across three days for experiments. The results indicate OSSMGNG achieves a higher classification accuracy than others. It suggests that the online semi-supervised learning algorithm enhances robustness of hand gesture identification against electrode shift.
Original languageEnglish
Title of host publicationProceedings of the 2016 International Conference on Machine Learning and Cybernetics
PublisherIEEE
Pages344-349
ISBN (Electronic)978-1-5090-0390-7
ISBN (Print)978-1-5090-0391-4
DOIs
Publication statusPublished - 23 Feb 2017
Event15th International Conference on Machine Learning and Cybernetics - Adelaide, Australia, Jeju Island, Korea, Republic of
Duration: 10 Jul 201613 Jul 2016
http://www.icmlc.com/

Publication series

Name
ISSN (Electronic)2160-1348

Conference

Conference15th International Conference on Machine Learning and Cybernetics
Abbreviated titleICMLC 2016
Country/TerritoryKorea, Republic of
CityJeju Island
Period10/07/1613/07/16
Internet address

Fingerprint

Dive into the research topics of 'Improving robustness against electrode shift of sEMG based hand gesture recognition using online semi-supervised learning'. Together they form a unique fingerprint.

Cite this